© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 113472
    Prev
    Next
    INDEX
    Explanations

    specific identifiers or codes

    np_acts-logits-general · gemini-2.5-flash-lite

    Business processes, decisions, U-Net, balloons

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     بیچ
    0.47
    期间
    0.44
     Characters
    0.42
    英语
    0.41
     anna
    0.41
     NSDictionary
    0.40
    ṃ
    0.40
     ය
    0.40
     キャ
    0.39
     ചാ
    0.39
    POSITIVE LOGITS
     воздействия
    0.50
    BUST
    0.50
    Hers
    0.48
     আইনের
    0.46
    Color
    0.46
    IO
    0.46
    瑩
    0.46
    YAN
    0.45
    orsi
    0.45
    jš
    0.44
    Activations Density 0.003%

    No Known Activations